Debiopharm extended its collaboration with Genialis to build a predictive biomarker for WEE1 therapy using the Supermodel.
DDR-targeted therapies such as WEE1 inhibitors lack accurate biomarkers for patient selection. The extended work uses the Genialis Supermodel, a large molecular model trained on hundreds of thousands of RNA-seq samples, to classify responders and non-responders for Debiopharm's Phase 1 WEE1 asset. The page gives no efficacy figures and plans a presentation at AACR 2025.
Genialis is an AI biomarker company offering the Supermodel and ResponderID to predict patient response in oncology drug development.
This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.
Published by Genialis on its own site — read the original case study on genialis.com ↗
Related use cases
- 01Genialis and Debiopharm began a collaboration to discover predictive biomarkers in DNA damage repair biology.
- 02Debiopharm deployed Genialis Expressions in its own cloud to standardize omics analysis for biomarker discovery.
- 03OpenAI's dedicated healthcare vertical page/launch post.
- 04Frontier reasoning model built for biology, drug discovery and translational medicine; named qualified customers include Amgen, Moderna, Allen Institute, and Thermo Fisher Scientific.
- 05follow-up update to the life-sciences model.
- 06"How Amgen uses GPT-5": Amgen applies GPT-5/frontier models to help accelerate delivery of potential new therapies; found GPT-5 met scientific-accuracy standards.